Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    াবাদ
    0.38
    muy
    0.37
     жизнью
    0.36
    diphenyl
    0.36
    бок
    0.35
     छत
    0.35
    ოლოგი
    0.35
    णं
    0.35
    kilomet
    0.35
    త్రి
    0.35
    POSITIVE LOGITS
     amateur
    0.50
     henne
    0.48
     amateurs
    0.48
     सामान्य
    0.45
    speak
    0.45
     vanlig
    0.45
     സാധാരണ
    0.44
     usual
    0.43
     pont
    0.43
     ಸಾಮಾನ್ಯ
    0.42
    Act Density 0.001%

    No Known Activations